The world’s population is growing and global food production is projected to need to double by 2050. Climate change brings challenges to agriculture due to unpredictable precipitation patterns and rising temperatures. At the same time, carbon dioxide (CO2) and other greenhouse gases continue to rise and increase global warming. Vertical farming can help support mitigation of the growing need for food and combined with capturing CO2 from the air to fertilize the plants, the climate is also positively influenced. This degree project investigated the effect of CO2 concentration on leaf net photosynthetic rate for selected plant species and assessed feasibility to build a model to predict the leaf net photosynthetic rate. A model based on an artificial neural network (ANN) was developed to predict the net photosynthetic rate based on a number of factors including CO2 concentration from a set of data on woody species. The photosynthetic response is expected to differ with the species, which is consistent with the results where a model based on a single species performed well with a high prediction accuracy. It was however also possible to develop an ANN model across all the species, as well as within a site, a family of species or a continent, albeit with a lower prediction accuracy than the model for a single species. The models can be updated to apply to vertical farming context and such models, especially cross-species, can be used to predict the net photosynthetic rate instead of measuring it using a photosynthesis system, which is a time-consuming process and requires special equipment.